Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    center

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lẫn
    -0.07
    _dependency
    -0.07
     nợ
    -0.07
    roy
    -0.06
     вигляді
    -0.06
    woke
    -0.06
     explanations
    -0.06
     GameManager
    -0.06
     meilleure
    -0.06
     ledge
    -0.06
    POSITIVE LOGITS
    :%
    0.07
     DATABASE
    0.07
    љ
    0.06
     highlight
    0.06
    Ne
    0.06
    SPORT
    0.06
    ervice
    0.06
     Cao
    0.06
    topic
    0.06
    _SI
    0.06
    Act Density 0.020%

    No Known Activations